Open Source Column

  • Procedural Content Generation – The Open Source Success Story of Wave Function Collapse

    Procedural Content Generation - The Open Source Success Story of Wave Function Collapse

      With OpenAI’s Dall-E, Midjourney, and Adobe Firefly, computer-generated visual content has hit the mass market. Machine learning-based algorithms can now create, and re-mix multimedia content based on huge corpora of images and videos and relieve creative professionals of tedious work. While this has gained much momentum lately, procedurally generated content (PCG) has been around for ...

  • Autonomous driving research with CARLA simulator

    Autonomous driving research with CARLA simulator

    Introduction The autonomous driving industry, in order to advance through its six levels of automation (as defined by SAE, Society of Automotive Engineers ), is going to be increasingly more data-driven. While the number of sensors and their technology has been increasing it is still both cost-effective and, in some cases, necessary to use a simulator, ...

  • COCO Annotator – Web-based Image Segmentation Tool for Object Detection, Localization, and Keypoints

    COCO Annotator - Web-based Image Segmentation Tool for Object Detection, Localization, and Keypoints

    Introduction COCO Annotator is an image annotation tool that allows the labelling of images to create training data for object detection and localization. It provides many features, including the ability to label an image segment by drawing, label objects with disconnected visible parts, efficiently store and export annotations in the well-known COCO format as well as ...

  • Multimedia Retrieval and Analysis with Cottontail DB

    Multimedia Retrieval and Analysis with Cottontail DB

    Introduction Analysis and retrieval of media collections get more and more challenging the larger the collections become. Keeping everything in the main memory becomes less feasible, and more and more time and effort have to be spent to deal with the data management. However, traditional relational databases do not support primitives often used in multimedia workloads, ...

  • Open Source for Video Games – A Shortlist of Game Engines

    Open Source for Video Games - A Shortlist of Game Engines

    Introduction Open-source software is a relevant topic in video game development. Taking a look at the most frequently employed game engines for developing Android games we can see that seven out of ten ranked engines are OSS. Over the last decade, more and more game studios and individual developers switched to open-source software. Oliver Franzke ...

  • nteract – A Desktop-Based Tool for Notebooks

    nteract - A Desktop-Based Tool for Notebooks

    Introduction Writing source code for programs with lightweight text editors or fully featured integrated development environments is considered the main method of programming. Notebooks, however, are an extremely practical tool. In contrast to IDEs, projects are set up more easily and they allow for running programs in a read-eval-print loop (REPL) environment. The Jupyter Notebooks Quick ...

  • Open Source Video Streaming & Recording

    Open Source Video Streaming & Recording

    By the time of writing, the CoViD-19 disease has spread, impacting the world. Education and research are affected as well, but fortunately the community can continue working due to all the developments over the last few years. Even more so, streaming tech and video conferences allow us to keep in touch with family and friends. ...

  • OpenVSLAM: A Versatile Visual SLAM Framework

    OpenVSLAM: A Versatile Visual SLAM Framework

    Visual simultaneous localization and mapping (VSLAM) systems are essential for augmented reality devices, autonomous control of robots and drones, etc. However, conventional open-source visual SLAM frameworks are not designed to be called as libraries from third-party programs. To overcome this situation, we have developed OpenVSLAM , a novel visual SLAM framework, and released it as ...

  • Configurable image annotation on the Web

    Configurable image annotation on the Web

    Image annotations are required in a wide range of applications including image classification (which requires textual labels), object detection (bounding boxes), or image segmentation (pixel-wise classification). The application we show here was presented in the ACM Multimedia 2018 Open Source Software Competition track, and provides a number of configurable manual image annotation tools for detection and segmentation. It is available online, but in ...

  • Deep Learning in the Browser: TensorFlow JS

    Having already discussed MatConvNet and Keras, let us continue with an open source framework for deep learning, which takes a new and interesting approach. TensorFlow.js is not only providing deep learning for JavaScript developers, but it’s also making applications of deep learning available in the WebGL enabled web browsers, or more specifically, Chrome, Chromium-based browsers, ...

  • Deep learning with Keras

    Deep learning with Keras

    Following the last column on MatConvNet, let us continue to look at open source frameworks for deep learning. In this column we are going to check Keras, a Python API that allows to use several different backends like Tensorflow and CNTK. Actually, it also supports Theano, although the development of this framework has been halted by the ...

  • Simulating Adaptive Video Streaming Using Sabre

    Simulating Adaptive Video Streaming Using Sabre

    Sabre . Sabre is ...

  • MatConvNet: CNNs are also for MATLAB users

    MatConvNet: CNNs are also for MATLAB users

    MatConvNet is an open source MATLAB toolbox implementing Convolutional Neural Networks (CNNs) for computer vision and multimedia applications, developed by the same authors of the famed VLFeat library. Both libraries have associated papers that have been presented within the Open Source Software Competition track of ACM Multimedia: “MatConvNet: Convolutional Neural Networks for MATLAB” and “Vlfeat: ...

  • Content-based Multimedia Retrieval using vitrivr

    Content-based Multimedia Retrieval using vitrivr

    vitrivr is an open source retrieval system capable of processing multimedia documents such as images, videos, music, and 3D-models. It supports a wealth of content based features for multiple modalities and comes with a ready-to-use Docker image and user interface. We focus on the vitrivr stack in its second version, comprised of ADAMPro  2.0.0, Cineast ...

  • UDLF: Unsupervised Distance Learning Framework for Multimedia Retrieval

    UDLF: Unsupervised Distance Learning Framework for Multimedia Retrieval

    The Unsupervised Distance Learning Framework (UDLF) is a software developed to facilitate the general use and evaluation of novel unsupervised learning methods. These methods aim at post-processing the ranking information for different tasks, being especially useful for multimedia retrieval. The major advantage of UDLF is that it provides a unified and extensive model for ...

  • Open Source Column – Introduction

    Open Source Column - Introduction

    “Open source software is software that can be freely accessed, used, changed, and shared (in modified or unmodified form) by anyone” (cp. https://opensource.org/osd). So open source software (OSS) is actually something that one or more people can work on, improve it, refine it, change it, adapt it and share or use it. Why would anyone ...

  • Open Dataset and Software Track @ ACM MMSys 2017

    The ACM Multimedia Systems Conference (MMSys) provides a forum for researchers to present and share their latest research findings in multimedia systems. While research about specific aspects of multimedia systems are regularly published in the various proceedings and transactions of the networking, operating system, realtime system, and database communities, MMSys aims to cut across these ...

  • MediaEval 2016 multimedia benchmark: Registration open—first data releases starting soon

    MediaEval offers shared-tasks in multimedia retrieval and analysis. Successful approaches make use of multiple modalities and go beyond visual content to also exploit audio, text, and other contextual information. For each task, participants receive a task definition, task data, and accompanying resources (dependent on task) such as keyframes, visual features, and social metadata. Register through ...

  • The Menpo Project

    The Menpo Project

    Overview The Menpo Project is a BSD-licensed set of tools and software designed to provide an end-to-end pipeline for collection and annotation of image and 3D mesh data. In particular, the Menpo Project provides tools for annotating images and meshes with a sparse set of fiducial markers that we refer to as landmarks. For example, ...

  • SIVA Suite: An Open-Source Framework for Hypervideos

    SIVA Suite: An Open-Source Framework for Hypervideos

    Overview The SIVA Suite is an open source framework for the creation, playback, and administration of hypervideos. Allowing the definition of complex navigational structures, our hypervideos are well suited for different scenarios. Compared to traditional linear videos, they especially excel in e-learning and training situations (see ), where fitting the teaching material to the ...

Comments are closed.